Towards Physics-Informed Graph Neural Network-based Computational Electromagnetics
Accepted version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Bakirtzis, Stefanos
Fiore, Marco
Wassell, Ian
Abstract
This paper presents a generalizable data-driven computational electromagnetics (CEM) framework leveraging graph neural networks (GNNs). The proposed model supports training and inference for CEM scenarios with different simulation domain sizes and electromagnetic properties, while exploiting the locality of GNNs to achieve reduced complexity and enhanced accuracy. Our results indicate that GNNs can successfully infer the electromagnetic field spatiotemporal evolution for arbitrary simulation domain setups, paving the way for fully-fledged data-driven CEM models.
Description
Keywords
Journal Title
Conference Name
2024 IEEE International Symposium on Antennas and Propagation and ITNC-USNC-URSI Radio Science Meeting
Journal ISSN
Volume Title
Publisher
Publisher DOI
Publisher URL
Sponsorship
The work of Stefanos Bakirtzis is supported by the Onassis Foundation and the Foundation for Education and
European Culture.